Artificial Intelligence
Episodes whose main subject is AI itself: building with, training, evaluating, or debating AI systems. AI used only as a tool for another topic goes to that topic.
#4469: The Missing Protocol for AI Software Development
No one has built a software development protocol designed for AI agents. Here's what that would require.
#4466: Free Your Shopping Cart: Dot Cart Explained
A new open file format lets you export, share, and compare shopping carts across any vendor.
#4465: True Crime Docuseries That Don't Earn Their Runtime
A countdown of docuseries that stretch thin stories across too many episodes — and the padding tricks they use.
#4462: How AI Imagines Your Skeleton
From image to fully rigged 3D model — the six computational stages that turn photos into animated characters.
#4458: How Headroom Compresses Agent Context Without Breaking Outputs
A deep dive into Headroom's content-aware compression pipeline that promises 20-95% token savings without changing agent answers.
#4457: OpenViking: A Filesystem for AI Agent Memory
OpenViking unifies memory, RAG, and skills into a browsable filesystem for AI agents — no vector database abstraction needed.
#4456: Inside the Podcast Pipeline: How 15 Weekly Episodes Get Made
From prompt to published episode — a full walkthrough of the automated production system running 15 shows weekly.
#4453: Workers vs Workflows: Recovering From SSD Failure
When your VPS SSD dies at 3AM, how do you know what broke? A practical guide to self-hosted worker management.
#4451: Python 3.14: Deferred Annotations, t-Strings & Free-Threaded Mode
Deferred annotations, t-strings, subinterpreters, and free-threaded mode — what actually changed in Python 3.14.
#4450: Intercepting Claude Code: The Proxy Ecosystem
How middleware proxies intercept, reroute, and transform AI tool traffic — and what it means for users.
#4449: Blur Before You Publish: Image Redaction Tools
How to automatically find and blur QR codes, credit cards, and sensitive text in photos before publishing.
#4448: The MK Claude Project: AI That Writes Political Manifestos
One citizen built a multi-agent AI to research, stress-test, and synthesize policy positions. The result? A forkable manifesto.
#4446: What Claude Fable 5's Suspension Reveals About AI Regulation
Three days after launch, the US government suspended Anthropic's Claude Fable 5. Here's what happened and why it matters.
#4445: AI Agents Keep Undoing Each Other's Work
Why AI coding agents silently revert each other's fixes — and three memory strategies that prevent it.
#4444: Testing the Unpredictable: QA for Agentic AI
How QA adapts when your AI system gives different answers to the same question every time.
#4442: When Prompt Enhancers Hallucinate Your Intent
How to build a prompt enhancer that doesn't rewrite your constraints into oblivion.
#4429: Talking to Humans Like AI Agents
Can Grice's maxims survive your spouse's system prompt? We map the uncanny valley of conversational efficiency.
#4427: ADB + Claude Code: Clean Up Your Android Phone
An AI agent plus a 20-year-old debugging tool can strip bloatware and fix apps without root.
#4419: 55M Addresses Leaked: What Suno Users Need to Know
Suno's breach exposed addresses and partial credit cards. What duty of care do companies owe when data becomes a physical threat?
#4415: Why Your Phone Scan Fails (and How to Fix It)
AI scanners are amazing—until they fail on glare or white paper. Here's how to fix it with stuff you already own.